Ops-dashboard/deploy/server-backup/restore-test.sh

#!/usr/bin/env bash
# Restore the latest restic snapshot to /tmp/restore-test/ and assert that a
# small set of critical files came back intact. Used by the monthly maintenance
# check and by the dashboard's "Restore test" button.
#
# Usage:
#   server-backup-restore-test.sh [nas|b2]
#
# Default repo is "nas" (faster, no B2 download fees).

umask 077
set -uo pipefail

REPO_LABEL="${1:-nas}"
RESTORE_DIR="${RESTORE_DIR:-/tmp/restore-test}"
RESTIC_PASSWORD_FILE_PATH="${RESTIC_PASSWORD_FILE_PATH:-/etc/restic-backup.password}"
STATUS_FILE="${STATUS_FILE:-/srv/backups/status/last-restore-test.json}"
STATUS_DIR="$(dirname "$STATUS_FILE")"
STARTED_AT="$(date -Is)"
SECONDS=0

# Load env (idempotent: ok if already in environment).
if [ -z "${RESTIC_REPO_NAS:-}" ] && [ -r /etc/restic-backup.env ]; then
  # shellcheck disable=SC1091
  set -a; . /etc/restic-backup.env; set +a
fi

case "$REPO_LABEL" in
  nas) REPO="${RESTIC_REPO_NAS:?RESTIC_REPO_NAS not set}" ;;
  b2)  REPO="${RESTIC_REPO_B2:?RESTIC_REPO_B2 not set}" ;;
  *)   echo "ERROR: repo label must be 'nas' or 'b2', got '$REPO_LABEL'" >&2; exit 2 ;;
esac

if [ ! -r "$RESTIC_PASSWORD_FILE_PATH" ]; then
  echo "ERROR: restic password file $RESTIC_PASSWORD_FILE_PATH not readable" >&2
  exit 1
fi
export RESTIC_PASSWORD_FILE="$RESTIC_PASSWORD_FILE_PATH"

for tool in jq restic; do
  command -v "$tool" >/dev/null 2>&1 || { echo "ERROR: '$tool' not on PATH" >&2; exit 1; }
done

mkdir -p "$STATUS_DIR"
chmod 0750 "$STATUS_DIR"

echo "════════════════════════════════════════════════════════════════"
echo " Restore test — started $STARTED_AT"
echo " Repo: $REPO_LABEL ($REPO)"
echo " Target: $RESTORE_DIR"
echo "════════════════════════════════════════════════════════════════"

# Clean previous attempt to keep results unambiguous.
rm -rf "$RESTORE_DIR"
mkdir -p "$RESTORE_DIR"

# Find latest snapshot id.
SNAPSHOT_ID=$(restic -r "$REPO" snapshots --json --latest 1 2>/dev/null \
  | jq -r '.[0].short_id // .[0].id // empty')

if [ -z "$SNAPSHOT_ID" ]; then
  echo "ERROR: no snapshots found in $REPO_LABEL repo"
  jq -n \
    --arg started "$STARTED_AT" \
    --arg completed "$(date -Is)" \
    --argjson duration "$SECONDS" \
    --arg repo "$REPO_LABEL" \
    '{
      schema_version: 1,
      overall_status: "failed",
      started_at: $started,
      completed_at: $completed,
      duration_seconds: $duration,
      repo: $repo,
      snapshot_id: null,
      error: "no snapshots in repo",
      assertions: []
    }' > "$STATUS_FILE"
  chmod 0644 "$STATUS_FILE"
  exit 1
fi

echo "Restoring snapshot $SNAPSHOT_ID …"
RESTORE_RC=0
restic -r "$REPO" restore "$SNAPSHOT_ID" --target "$RESTORE_DIR" || RESTORE_RC=$?

if [ "$RESTORE_RC" -ne 0 ]; then
  echo "ERROR: restic restore exited $RESTORE_RC"
fi

# Assertions: each is a path that MUST exist and be non-empty.
# Adjust to your stack after first run (and update the runbook addendum).
ASSERTION_PATHS=(
  "$RESTORE_DIR/srv/scrum4me/compose/docker-compose.yml"
  "$RESTORE_DIR/srv/scrum4me/caddy/Caddyfile"
  "$RESTORE_DIR/etc/restic-backup.env"
)

# Latest postgres dump — match the newest file (glob may resolve to zero).
shopt -s nullglob
PG_DUMPS=("$RESTORE_DIR/var/backups/databases/"postgres-*.sql.gz)
shopt -u nullglob
if [ "${#PG_DUMPS[@]}" -gt 0 ]; then
  # pick lexicographic last (= newest date, ISO format)
  LATEST_PG="${PG_DUMPS[-1]}"
  ASSERTION_PATHS+=("$LATEST_PG")
fi

ASSERTIONS_JSON='[]'
ANY_FAILED=0
for p in "${ASSERTION_PATHS[@]}"; do
  if [ -s "$p" ]; then
    status="ok"
    bytes=$(stat -c %s "$p")
    echo "  ✓ $p ($bytes bytes)"
  elif [ -e "$p" ]; then
    status="empty"
    bytes=0
    ANY_FAILED=1
    echo "  ✗ $p (exists but empty)"
  else
    status="missing"
    bytes=0
    ANY_FAILED=1
    echo "  ✗ $p (missing)"
  fi
  ASSERTIONS_JSON=$(jq -c \
    --arg path "$p" \
    --arg status "$status" \
    --argjson bytes "$bytes" \
    '. + [{path: $path, status: $status, bytes: $bytes}]' \
    <<< "$ASSERTIONS_JSON")
done

if [ "$RESTORE_RC" -ne 0 ]; then
  OVERALL="failed"
elif [ "$ANY_FAILED" -ne 0 ]; then
  OVERALL="partial_failure"
else
  OVERALL="success"
fi

jq -n \
  --arg started "$STARTED_AT" \
  --arg completed "$(date -Is)" \
  --argjson duration "$SECONDS" \
  --arg repo "$REPO_LABEL" \
  --arg snapshot "$SNAPSHOT_ID" \
  --arg overall "$OVERALL" \
  --argjson restore_exit "$RESTORE_RC" \
  --argjson assertions "$ASSERTIONS_JSON" \
  '{
    schema_version: 1,
    overall_status: $overall,
    started_at: $started,
    completed_at: $completed,
    duration_seconds: $duration,
    repo: $repo,
    snapshot_id: $snapshot,
    restore_exit_code: $restore_exit,
    target: "'"$RESTORE_DIR"'",
    assertions: $assertions
  }' > "$STATUS_FILE"
chmod 0644 "$STATUS_FILE"

echo ""
echo "════════════════════════════════════════════════════════════════"
echo " Restore test — finished $(date -Is)"
echo " Overall: $OVERALL"
echo " Status file: $STATUS_FILE"
echo "════════════════════════════════════════════════════════════════"

case "$OVERALL" in
  success) exit 0 ;;
  partial_failure) exit 75 ;;
  failed|*) exit 1 ;;
esac